How can I count the number of times a particular string occurs in another string. For example, this is what I am trying to do in Javascript:
var temp = "This is a string.";
alert(temp.count("is")); //should output '2'
How can I count the number of times a particular string occurs in another string. For example, this is what I am trying to do in Javascript:
var temp = "This is a string.";
alert(temp.count("is")); //should output '2'
The g
in the regular expression (short for global) says to search the whole string rather than just find the first occurrence. This matches is
twice:
var temp = "This is a string.";
var count = (temp.match(/is/g) || []).length;
console.log(count);
And, if there are no matches, it returns 0
:
var temp = "Hello World!";
var count = (temp.match(/is/g) || []).length;
console.log(count);
/** Function that count occurrences of a substring in a string;
* @param {String} string The string
* @param {String} subString The sub string to search for
* @param {Boolean} [allowOverlapping] Optional. (Default:false)
*
* @author Vitim.us https://gist.github.com/victornpb/7736865
* @see Unit Test https://jsfiddle.net/Victornpb/5axuh96u/
* @see http://stackoverflow.com/questions/4009756/how-to-count-string-occurrence-in-string/7924240#7924240
*/
function occurrences(string, subString, allowOverlapping) {
string += "";
subString += "";
if (subString.length <= 0) return (string.length + 1);
var n = 0,
pos = 0,
step = allowOverlapping ? 1 : subString.length;
while (true) {
pos = string.indexOf(subString, pos);
if (pos >= 0) {
++n;
pos += step;
} else break;
}
return n;
}
occurrences("foofoofoo", "bar"); //0
occurrences("foofoofoo", "foo"); //3
occurrences("foofoofoo", "foofoo"); //1
occurrences("foofoofoo", "foofoo", true); //2
Matches:
foofoofoo
1 `----´
2 `----´
I've made a benchmark test and my function is more then 10 times faster then the regexp match function posted by gumbo. In my test string is 25 chars length. with 2 occurences of the character 'o'. I executed 1 000 000 times in Safari.
Safari 5.1
Benchmark> Total time execution: 5617 ms (regexp)
Benchmark> Total time execution: 881 ms (my function 6.4x faster)
Firefox 4
Benchmark> Total time execution: 8547 ms (Rexexp)
Benchmark> Total time execution: 634 ms (my function 13.5x faster)
Edit: changes I've made
cached substring length
added type-casting to string.
added optional 'allowOverlapping' parameter
fixed correct output for "" empty substring case.
Just code-golfing Rebecca Chernoff's solution :-)
alert(("This is a string.".match(/is/g) || []).length);
Here is the fastest function!
Why is it faster?
All operations are as combined as they can be, avoiding slowdowns due to multiple operations
String.prototype.timesCharExist=function(c){var t=0,l=0,c=(c+'')[0];while(l=this.indexOf(c,l)+1)++t;return t};
Here is a slower and more readable version:
String.prototype.timesCharExist = function ( chr ) {
var total = 0, last_location = 0, single_char = ( chr + '' )[0];
while( last_location = this.indexOf( single_char, last_location ) + 1 )
{
total = total + 1;
}
return total;
};
This one is slower because of the counter, long var names and misuse of 1 var.
To use it, you simply do this:
'The char "a" only shows up twice'.timesCharExist('a');
Edit: (2013/12/16)
DON'T use with Opera 12.16 or older! it will take almost 2.5x more than the regex solution!
On chrome, this solution will take between 14ms and 20ms for 1,000,000 characters.
The regex solution takes 11-14ms for the same amount.
Using a function (outside String.prototype
) will take about 10-13ms.
Here is the code used:
String.prototype.timesCharExist=function(c){var t=0,l=0,c=(c+'')[0];while(l=this.indexOf(c,l)+1)++t;return t};
var x=Array(100001).join('1234567890');
console.time('proto');x.timesCharExist('1');console.timeEnd('proto');
console.time('regex');x.match(/1/g).length;console.timeEnd('regex');
var timesCharExist=function(x,c){var t=0,l=0,c=(c+'')[0];while(l=x.indexOf(c,l)+1)++t;return t;};
console.time('func');timesCharExist(x,'1');console.timeEnd('func');
The result of all the solutions should be 100,000!
Note: if you want this function to count more than 1 char, change where is c=(c+'')[0]
into c=c+''
I think the purpose for regex is much different from indexOf
.
indexOf
simply find the occurance of a certain string while in regex you can use wildcards like [A-Z]
which means it will find any capital character in the word without stating the actual character.
Example:
var index = "This is a string".indexOf("is");
console.log(index);
var length = "This is a string".match(/[a-z]/g).length;
// where [a-z] is a regex wildcard expression thats why its slower
console.log(length);
Super duper old, but I needed to do something like this today and only thought to check SO afterwards. Works pretty fast for me.
String.prototype.count = function(substr,start,overlap) {
overlap = overlap || false;
start = start || 0;
var count = 0,
offset = overlap ? 1 : substr.length;
while((start = this.indexOf(substr, start) + offset) !== (offset - 1))
++count;
return count;
};
var myString = "This is a string.";
var foundAtPosition = 0;
var Count = 0;
while (foundAtPosition != -1)
{
foundAtPosition = myString.indexOf("is",foundAtPosition);
if (foundAtPosition != -1)
{
Count++;
foundAtPosition++;
}
}
document.write("There are " + Count + " occurrences of the word IS");
Refer :- count a substring appears in the string for step by step explanation.
Building upon @Vittim.us answer above. I like the control his method gives me, making it easy to extend, but I needed to add case insensitivity and limit matches to whole words with support for punctuation. (e.g. "bath" is in "take a bath." but not "bathing")
The punctuation regex came from: https://stackoverflow.com/a/25575009/497745 (How can I strip all punctuation from a string in JavaScript using regex?)
function keywordOccurrences(string, subString, allowOverlapping, caseInsensitive, wholeWord)
{
string += "";
subString += "";
if (subString.length <= 0) return (string.length + 1); //deal with empty strings
if(caseInsensitive)
{
string = string.toLowerCase();
subString = subString.toLowerCase();
}
var n = 0,
pos = 0,
step = allowOverlapping ? 1 : subString.length,
stringLength = string.length,
subStringLength = subString.length;
while (true)
{
pos = string.indexOf(subString, pos);
if (pos >= 0)
{
var matchPos = pos;
pos += step; //slide forward the position pointer no matter what
if(wholeWord) //only whole word matches are desired
{
if(matchPos > 0) //if the string is not at the very beginning we need to check if the previous character is whitespace
{
if(!/[\s\u2000-\u206F\u2E00-\u2E7F\\'!"#$%&\(\)*+,\-.\/:;<=>?@\[\]^_`{|}~]/.test(string[matchPos - 1])) //ignore punctuation
{
continue; //then this is not a match
}
}
var matchEnd = matchPos + subStringLength;
if(matchEnd < stringLength - 1)
{
if (!/[\s\u2000-\u206F\u2E00-\u2E7F\\'!"#$%&\(\)*+,\-.\/:;<=>?@\[\]^_`{|}~]/.test(string[matchEnd])) //ignore punctuation
{
continue; //then this is not a match
}
}
}
++n;
} else break;
}
return n;
}
Please feel free to modify and refactor this answer if you spot bugs or improvements.
For anyone that finds this thread in the future, note that the accepted answer will not always return the correct value if you generalize it, since it will choke on regex operators like $
and .
. Here's a better version, that can handle any needle:
function occurrences (haystack, needle) {
var _needle = needle
.replace(/\[/g, '\\[')
.replace(/\]/g, '\\]')
return (
haystack.match(new RegExp('[' + _needle + ']', 'g')) || []
).length
}
Now this is a very old thread i've come across but as many have pushed their answer's, here is mine in a hope to help someone with this simple code.
var search_value = "This is a dummy sentence!";
var letter = 'a'; /*Can take any letter, have put in a var if anyone wants to use this variable dynamically*/
letter = letter && "string" === typeof letter ? letter : "";
var count;
for (var i = count = 0; i < search_value.length; count += (search_value[i++] == letter));
console.log(count);
I'm not sure if it is the fastest solution but i preferred it for simplicity and for not using regex (i just don't like using them!)
ES2020 offers a new MatchAll which might be of use in this particular context.
Here we create a new RegExp, please ensure you pass 'g' into the function.
Convert the result using Array.from and count the length, which returns 2 as per the original requestor's desired output.
let strToCheck = RegExp('is', 'g')
let matchesReg = "This is a string.".matchAll(strToCheck)
console.log(Array.from(matchesReg).length) // 2
A simple way would be to split the string on the required word, the word for which we want to calculate the number of occurences, and subtract 1 from the number of parts:
function checkOccurences(string, word) {
return string.split(word).length - 1;
}
const text="Let us see. see above, see below, see forward, see backward, see left, see right until we will be right";
const count=countOccurences(text,"see "); // 2
var countInstances = function(body, target) {
var globalcounter = 0;
var concatstring = '';
for(var i=0,j=target.length;i<body.length;i++){
concatstring = body.substring(i-1,j);
if(concatstring === target){
globalcounter += 1;
concatstring = '';
}
}
return globalcounter;
};
console.log( countInstances('abcabc', 'abc') ); // ==> 2
console.log( countInstances('ababa', 'aba') ); // ==> 2
console.log( countInstances('aaabbb', 'ab') ); // ==> 1
substr_count
translated to Javascript from php
function substr_count (haystack, needle, offset, length) {
// eslint-disable-line camelcase
// discuss at: https://locutus.io/php/substr_count/
// original by: Kevin van Zonneveld (https://kvz.io)
// bugfixed by: Onno Marsman (https://twitter.com/onnomarsman)
// improved by: Brett Zamir (https://brett-zamir.me)
// improved by: Thomas
// example 1: substr_count('Kevin van Zonneveld', 'e')
// returns 1: 3
// example 2: substr_count('Kevin van Zonneveld', 'K', 1)
// returns 2: 0
// example 3: substr_count('Kevin van Zonneveld', 'Z', 0, 10)
// returns 3: false
var cnt = 0
haystack += ''
needle += ''
if (isNaN(offset)) {
offset = 0
}
if (isNaN(length)) {
length = 0
}
if (needle.length === 0) {
return false
}
offset--
while ((offset = haystack.indexOf(needle, offset + 1)) !== -1) {
if (length > 0 && (offset + needle.length) > length) {
return false
}
cnt++
}
return cnt
}
Check out Locutus's Translation Of Php's substr_count function
The parameters: ustring: the superset string countChar: the substring
A function to count substring occurrence in JavaScript:
function subStringCount(ustring, countChar){
var correspCount = 0;
var corresp = false;
var amount = 0;
var prevChar = null;
for(var i=0; i!=ustring.length; i++){
if(ustring.charAt(i) == countChar.charAt(0) && corresp == false){
corresp = true;
correspCount += 1;
if(correspCount == countChar.length){
amount+=1;
corresp = false;
correspCount = 0;
}
prevChar = 1;
}
else if(ustring.charAt(i) == countChar.charAt(prevChar) && corresp == true){
correspCount += 1;
if(correspCount == countChar.length){
amount+=1;
corresp = false;
correspCount = 0;
prevChar = null;
}else{
prevChar += 1 ;
}
}else{
corresp = false;
correspCount = 0;
}
}
return amount;
}
console.log(subStringCount('Hello World, Hello World', 'll'));
Iterate less the second time (just when first letter of substring matches) but still uses 2 for loops:
function findSubstringOccurrences(str, word) {
let occurrences = 0;
for(let i=0; i<str.length; i++){
if(word[0] === str[i]){ // to make it faster and iterate less
for(let j=0; j<word.length; j++){
if(str[i+j] !== word[j]) break;
if(j === word.length - 1) occurrences++;
}
}
}
return occurrences;
}
console.log(findSubstringOccurrences("jdlfkfomgkdjfomglo", "omg"));
//Try this code
const countSubStr = (str, search) => {
let arrStr = str.split('');
let i = 0, count = 0;
while(i < arrStr.length){
let subStr = i + search.length + 1 <= arrStr.length ?
arrStr.slice(i, i+search.length).join('') :
arrStr.slice(i).join('');
if(subStr === search){
count++;
arrStr.splice(i, search.length);
}else{
i++;
}
}
return count;
}